CN110493584A - A kind of high dynamic range environment Visualization method, apparatus and storage medium - Google Patents
A kind of high dynamic range environment Visualization method, apparatus and storage medium Download PDFInfo
- Publication number
- CN110493584A CN110493584A CN201910602158.9A CN201910602158A CN110493584A CN 110493584 A CN110493584 A CN 110493584A CN 201910602158 A CN201910602158 A CN 201910602158A CN 110493584 A CN110493584 A CN 110493584A
- Authority
- CN
- China
- Prior art keywords
- dynamic range
- high dynamic
- component
- formula
- color
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007794 visualization technique Methods 0.000 title claims abstract description 23
- 230000006835 compression Effects 0.000 claims abstract description 35
- 238000007906 compression Methods 0.000 claims abstract description 35
- 238000012800 visualization Methods 0.000 claims abstract description 22
- 238000006243 chemical reaction Methods 0.000 claims abstract description 12
- 230000003044 adaptive effect Effects 0.000 claims abstract description 11
- 230000010365 information processing Effects 0.000 claims abstract description 9
- 238000011084 recovery Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000010606 normalization Methods 0.000 claims abstract description 6
- 230000004927 fusion Effects 0.000 claims abstract description 3
- 238000004590 computer program Methods 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/186—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/77—Circuits for processing the brightness signal and the chrominance signal relative to each other, e.g. adjusting the phase of the brightness signal relative to the colour signal, correcting differential gain or differential phase
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/77—Circuits for processing the brightness signal and the chrominance signal relative to each other, e.g. adjusting the phase of the brightness signal relative to the colour signal, correcting differential gain or differential phase
- H04N9/78—Circuits for processing the brightness signal and the chrominance signal relative to each other, e.g. adjusting the phase of the brightness signal relative to the colour signal, correcting differential gain or differential phase for separating the brightness signal or the chrominance signal from the colour television signal, e.g. using comb filter
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20208—High dynamic range [HDR] image processing
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of high dynamic range environment Visualization method, apparatus and storage mediums.This method comprises: obtaining high dynamic range scene image；Color space conversion is carried out to the high dynamic range scene image, obtains luminance component and color component；Log-domain normalized is carried out to the luminance component, utilize the structure components and texture component of Total Variation model extraction normalization luminance picture, adaptive dynamic range compression is carried out to the structure components, obtain compression output, the fusion of texture information based on Taylor series is carried out to the texture component and the compression output, the luminance information rebuild is obtained, color information processing is carried out to the color component；Color information recovery is carried out according to the luminance information of the reconstruction and processed color component, obtains visualization result.Technical solution of the present invention can effectively realize high dynamic range environment Visualization, and can be used for real-time visual image processing system.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of high dynamic range environment Visualization method, apparatus
And storage medium.
Background technique
Reality scene has very high dynamic range, and for dynamic range up to 9 orders of magnitude, high dynamic range scene can be with
Scene information abundant and gorgeous color is presented, gives the more true scene feeling of people.Completely by high dynamic range scene
The technology being shown on general display devices is known as high dynamic range environment Visualization.
Currently, high dynamic range reality scene visualization technique be widely used in 3D film, intelligent monitoring, satellite remote sensing with
And the fields such as portable imaging device.Since existing imaging device and display its dynamic range of equipment only have 3 orders of magnitude, because
This can not be truly reflected the complete information of reality scene.High dynamic range reality scene visualization technique mainly includes tone pressure
Contracting and more exposure images merge both approach, and the dynamic range of scene directly compress then output general by tone compression
On logical display, more exposure image fusions are shown again after being synthesized the information of scene using the method for image co-registration.But
There are problems that scene information is not abundant enough and color distortion.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of high dynamic range environment Visualization method, apparatus and storage
Medium.
In a first aspect, this method comprises the following steps the present invention provides a kind of high dynamic range environment Visualization method:
Obtain high dynamic range scene image.
Color space conversion is carried out to the high dynamic range scene image, obtains luminance component and color component.
Log-domain normalized is carried out to the luminance component, is normalized using Total Variation model extraction
The structure components and texture component of luminance picture carry out adaptive dynamic range compression to the structure components, it is defeated to obtain compression
Out, are carried out by the texture information based on Taylor series and is merged for the texture component and the compression output, obtain the brightness of reconstruction
Information carries out color information processing to the color component.
Color information recovery is carried out according to the luminance information of the reconstruction and processed color component, obtains visualization knot
Fruit.
Second aspect, the present invention provides a kind of high dynamic range environment Visualization device, which includes:
Module is obtained, for obtaining high dynamic range scene image.
Conversion module, for the high dynamic range scene image carry out color space conversion, obtain luminance component and
Color component.
Processing module utilizes Total Variation mould for carrying out log-domain normalized to the luminance component
Type extracts the structure components and texture component of normalization luminance picture, carries out adaptive dynamic range pressure to the structure components
Contracting obtains compression output, and the texture component and the compression output are carried out the texture information based on Taylor series and merged, is obtained
The luminance information that must be rebuild carries out color information processing to the color component.
Recovery module, it is extensive for carrying out color information according to the luminance information of the reconstruction and processed color component
It is multiple, obtain visualization result.
The third aspect, the present invention provides a kind of high dynamic range environment Visualization device, the device include memory and
Processor；The memory, for storing computer program；The processor is used for when loaded and executed, real
Now high dynamic range environment Visualization method as described above.
Fourth aspect is stored with computer on the storage medium the present invention provides a kind of computer readable storage medium
Program realizes high dynamic range environment Visualization method as described above when the computer program is executed by processor.
High dynamic range environment Visualization method, apparatus provided by the invention and the beneficial effect of storage medium be, not only
All visual informations of scene can completely be presented, and computational efficiency is higher, can get lively, natural visualization result,
High dynamic range environment Visualization is had effectively achieved, and can be used for real-time visual image processing system, thus by high
Dynamic range reality scene shadow abundant and color are completely presented in common display equipment.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow diagram of the high dynamic range environment Visualization method of the embodiment of the present invention；
Fig. 2 is the structural block diagram of the high dynamic range environment Visualization device of the embodiment of the present invention.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the invention.
As shown in Figure 1, a kind of high dynamic range environment Visualization method provided in an embodiment of the present invention includes the following steps:
Obtain high dynamic range scene image.
Color space conversion is carried out to the high dynamic range scene image, obtains luminance component and color component.
Log-domain normalized is carried out to the luminance component, is normalized using Total Variation model extraction
The structure components and texture component of luminance picture carry out adaptive dynamic range compression to the structure components, it is defeated to obtain compression
Out, are carried out by the texture information based on Taylor series and is merged for the texture component and the compression output, obtain the brightness of reconstruction
Information carries out color information processing to the color component.
Color information recovery is carried out according to the luminance information of the reconstruction and processed color component, obtains visualization knot
Fruit.
In the present embodiment, all visual informations of scene not only can completely be presented, and computational efficiency is higher, can obtains
Vividly, natural visualization result, have effectively achieved high dynamic range environment Visualization, and can be used for visual in real time
Change image processing system, so that high dynamic range reality scene shadow abundant and color are completely presented on common display
In equipment.
Preferably, it is described to the high dynamic range scene image carry out color space conversion specific implementation include:
The high dynamic range scene image is transformed into HSV color space from rgb color space, obtain hue information H,
Saturation infromation S and luminance information V, wherein the luminance component includes the luminance information V, and the color component includes institute
State hue information H and the saturation infromation S.
In the preferred embodiment, high dynamic range scene image is transformed into HSV color space from rgb color space,
Perception due to HSV color space close to human visual system to reality scene color, and HSV space divides the brightness of scene
Amount and color component independently and separately, the color information of scene can be preferably kept while compression of dynamic range, makes picture
Face is more lively natural.
Preferably, it is described to the luminance component carry out log-domain normalized specific implementation include:
Log-domain normalized, first formula are carried out to the luminance component according to the first formula are as follows:
Wherein, VlogIndicate the normalized brightness value of log-domain, VmaxIndicate the maximum value of the luminance component.
In the preferred embodiment, since the vision system of the mankind is to the perception of scene brightness relatively logarithmic curve,
And structure components and texture component are extracted for convenience, the luminance component of scene is normalized, to meet the mankind
Perception of the vision system to scene brightness.
Preferably, the structure components and texture using Total Variation model extraction normalization luminance picture
The specific implementation of component includes:
The structure components, second formula are determined according to the second formula and third formula are as follows:
The third formula are as follows:
Wherein, ISIt indicates the structure components, includes biggish object in scene, the side for using half quadratic power to divide
Method acquires, and i indicates the serial number of pixel in image, i.e. ith pixel in image, and λ indicates smoothing factor.
The texture component, the 4th formula are determined according to the 4th formula are as follows:
IT=Vlog-Is。
Wherein, ITIt indicates the texture component, includes the texture information of scene, i.e. high fdrequency component.
In the preferred embodiment, Total Variation model is widely used in image denoising, due to its with it is each to
Anisotropic feature can protect well the edge and textural characteristics of image while efficiently reducing picture noise.
Preferably, it is described to the structure components carry out adaptive dynamic range compression specific implementation include:
Adaptive dynamic range compression is carried out to the structure components according to the 5th formula and the 6th formula, using arcsine
The 5th formula of function are as follows:
FcIt can be expressed by the 6th formula for compressibility factor in order to adapt to the dynamic range compression of different scenes, described
Six formula are as follows:
Wherein, VgIndicate the compression output,Indicate the average value of the structure components.
In the preferred embodiment, since structure components include biggish object in scene, there is very high dynamic range,
Texture component mainly includes the texture information of scene, and dynamic range is small, therefore, only carries out dynamic range pressure to structure components
Contracting.Arcsin function can effectively compression of dynamic range, and scene clear zone and dark space information can be retained well.
Preferably, described that is carried out by the texture information based on Taylor series and is merged with the compression output for the texture component
Specific implementation include:
Are carried out by the texture information based on Taylor series and is melted for the texture component and compression output according to the 7th formula
It closes, the 7th formula are as follows:
VTdr=f (Is)+f′(Is)IT。
Wherein, VldrIndicate the luminance information of the reconstruction, f (Is) indicate the 5th formula, i.e. dynamic range compression mistake
Journey, f ' (Is) indicate the first derivative of the 5th formula, f ' (Is)ITIndicate texture information treatment process.
In the preferred embodiment, due to compression equation be it is nonlinear, directly texture information cannot be added to compression
Export VgOn, in order to obtain satisfactory scene image, according to Taylor series f (x) ≈ f (x0)+f′(x0)(x-x0) obtain
Vldr=f (Is+IT)≈f(Is)+f′(Is)IT, and then obtain the 7th formula.
Preferably, it is described to the color component carry out color information processing specific implementation include:
The saturation infromation S is adjusted according to the 8th formula, using the 8th formula of sigmoid function are as follows:
Wherein, SldrIndicate processed saturation infromation.
Finally by the luminance information V of reconstructionldr, processed saturation infromation SldrAnd the hue information H of scene is from HSV
Color space is transformed into rgb color space, obtains high dynamic range environment Visualization image.
As shown in Fig. 2, a kind of high dynamic range environment Visualization device provided in an embodiment of the present invention includes:
Module is obtained, for obtaining high dynamic range scene image.
Conversion module, for the high dynamic range scene image carry out color space conversion, obtain luminance component and
Color component.
Processing module utilizes Total Variation mould for carrying out log-domain normalized to the luminance component
Type extracts the structure components and texture component of normalization luminance picture, carries out adaptive dynamic range pressure to the structure components
Contracting obtains compression output, and the texture component and the compression output are carried out the texture information based on Taylor series and merged, is obtained
The luminance information that must be rebuild carries out color information processing to the color component.
Recovery module, it is extensive for carrying out color information according to the luminance information of the reconstruction and processed color component
It is multiple, obtain visualization result.
In an alternative embodiment of the invention, a kind of high dynamic range environment Visualization device includes memory and processor.
The memory, for storing computer program.The processor, it is as above for when loaded and executed, realizing
The high dynamic range environment Visualization method.The device can be the computer installations such as PC machine, server.
In an alternative embodiment of the invention, it is stored with computer program on a kind of computer readable storage medium, when described
When computer program is executed by processor, high dynamic range environment Visualization method as described above is realized.
Reader should be understood that in the description of this specification reference term " one embodiment ", " is shown " some embodiments "
The description of example ", specific examples or " some examples " etc. mean specific features described in conjunction with this embodiment or example, structure,
Material or feature are included at least one embodiment or example of the invention.In the present specification, above-mentioned term is shown
The statement of meaning property need not be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of high dynamic range environment Visualization method, which comprises the steps of:
Obtain high dynamic range scene image；
Color space conversion is carried out to the high dynamic range scene image, obtains luminance component and color component；
Log-domain normalized is carried out to the luminance component, normalizes brightness using Total Variation model extraction
The structure components and texture component of image carry out adaptive dynamic range compression to the structure components, obtain compression output, right
The texture component and the compression output carry out the fusion of the texture information based on Taylor series, obtain the luminance information of reconstruction,
Color information processing is carried out to the color component；
Color information recovery is carried out according to the luminance information of the reconstruction and processed color component, obtains visualization result.
2. high dynamic range environment Visualization method according to claim 1, which is characterized in that described to the high dynamic
Range scene image carry out color space conversion specific implementation include:
The high dynamic range scene image is transformed into HSV color space from rgb color space, obtains hue information H, saturation
Spend information S and luminance information V, wherein the luminance component includes the luminance information V, and the color component includes the color
Adjust the information H and saturation infromation S.
3. high dynamic range environment Visualization method according to claim 2, which is characterized in that described to the brightness point
Amount carry out log-domain normalized specific implementation include:
Log-domain normalized, first formula are carried out to the luminance component according to the first formula are as follows:
Wherein, VlogIndicate the normalized brightness value of log-domain, VmaxIndicate the maximum value of the luminance component.
4. high dynamic range environment Visualization method according to claim 2, which is characterized in that described to utilize Total
The specific implementation of structure components and texture component of Variation model extraction normalization luminance picture includes:
The structure components, second formula are determined according to the second formula and third formula are as follows:
The third formula are as follows:
Wherein, ISIndicate that the structure components, i indicate the serial number of pixel in image, λ indicates smoothing factor；
The texture component, the 4th formula are determined according to the 4th formula are as follows:
IT=Vlog-Is；
Wherein, ITIndicate the texture component.
5. high dynamic range environment Visualization method according to claim 4, which is characterized in that described to the structure point
Amount carry out adaptive dynamic range compression specific implementation include:
Adaptive dynamic range compression, the 5th formula are carried out to the structure components according to the 5th formula and the 6th formula
Are as follows:
6th formula are as follows:
Wherein, VgIndicate the compression output,Indicate the average value of the structure components.
6. high dynamic range environment Visualization method according to claim 5, which is characterized in that described to the texture point
Amount and the compression output carry out the specific implementation that the texture information based on Taylor series merges and include:
Are carried out by the texture information based on Taylor series and is merged for the texture component and the compression output according to the 7th formula, institute
State the 7th formula are as follows:
Vldr=f (Is)+f′(Is)IT；
Wherein, VldrIndicate the luminance information of the reconstruction, f (Is) indicate the 5th formula, f ' (Is) indicate that the described 5th is public
The first derivative of formula.
7. high dynamic range environment Visualization method according to claim 2, which is characterized in that described to the color point
Amount carry out color information processing specific implementation include:
The saturation infromation S, the 8th formula are adjusted according to the 8th formula are as follows:
Wherein, SldrIndicate processed saturation infromation.
8. a kind of high dynamic range environment Visualization device characterized by comprising
Module is obtained, for obtaining high dynamic range scene image；
Conversion module obtains luminance component and color for carrying out color space conversion to the high dynamic range scene image
Component；
Processing module is mentioned for carrying out log-domain normalized to the luminance component using Total Variation model
The structure components and texture component for taking normalization luminance picture carry out adaptive dynamic range compression to the structure components, obtain
Output must be compressed, are carried out by the texture information based on Taylor series and is merged for the texture component and the compression output, is weighed
The luminance information built carries out color information processing to the color component；
Recovery module is obtained for carrying out color information recovery according to the luminance information of the reconstruction and processed color component
Obtain visualization result.
9. a kind of high dynamic range environment Visualization device, which is characterized in that including memory and processor；
The memory, for storing computer program；
The processor, it is as described in any one of claim 1 to 7 high dynamic for when loaded and executed, realizing
State range environment Visualization method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer program on the storage medium, work as institute
When stating computer program and being executed by processor, high dynamic range environment Visualization as described in any one of claim 1 to 7 is realized
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910602158.9A CN110493584B (en) | 2019-07-05 | 2019-07-05 | High dynamic range scene visualization method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910602158.9A CN110493584B (en) | 2019-07-05 | 2019-07-05 | High dynamic range scene visualization method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110493584A true CN110493584A (en) | 2019-11-22 |
| CN110493584B CN110493584B (en) | 2022-04-29 |
Family
ID=68546719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910602158.9A Active CN110493584B (en) | 2019-07-05 | 2019-07-05 | High dynamic range scene visualization method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110493584B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113436167A (en) * | 2021-06-25 | 2021-09-24 | 湖南工商大学 | No-reference color image quality evaluation method based on deep learning and visual perception |
| CN116152369A (en) * | 2022-12-31 | 2023-05-23 | 廊坊奎达信息技术有限公司 | Image dynamic visualization method based on big data technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102938837A (en) * | 2012-09-19 | 2013-02-20 | 中山大学 | Tone mapping method based on edge preservation total variation model |
| US20160289637A1 (en) * | 2015-04-03 | 2016-10-06 | Dana-Farber Cancer Institute, Inc. | Composition and methods of genome editing of b-cells |
| CN107657594A (en) * | 2017-09-22 | 2018-02-02 | 武汉大学 | The quick tone mapping method and system of a kind of high quality |
| CN108898564A (en) * | 2018-07-06 | 2018-11-27 | 中国科学院光电技术研究所 | High dynamic range image tone mapping method based on human visual model and W L S filter |
-
2019
- 2019-07-05 CN CN201910602158.9A patent/CN110493584B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102938837A (en) * | 2012-09-19 | 2013-02-20 | 中山大学 | Tone mapping method based on edge preservation total variation model |
| US20160289637A1 (en) * | 2015-04-03 | 2016-10-06 | Dana-Farber Cancer Institute, Inc. | Composition and methods of genome editing of b-cells |
| CN107657594A (en) * | 2017-09-22 | 2018-02-02 | 武汉大学 | The quick tone mapping method and system of a kind of high quality |
| CN108898564A (en) * | 2018-07-06 | 2018-11-27 | 中国科学院光电技术研究所 | High dynamic range image tone mapping method based on human visual model and W L S filter |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113436167A (en) * | 2021-06-25 | 2021-09-24 | 湖南工商大学 | No-reference color image quality evaluation method based on deep learning and visual perception |
| CN113436167B (en) * | 2021-06-25 | 2022-04-26 | 湖南工商大学 | No-reference color image quality evaluation method based on deep learning and visual perception |
| CN116152369A (en) * | 2022-12-31 | 2023-05-23 | 廊坊奎达信息技术有限公司 | Image dynamic visualization method based on big data technology |
| CN116152369B (en) * | 2022-12-31 | 2023-09-22 | 廊坊奎达信息技术有限公司 | Image dynamic visualization method based on big data technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110493584B (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liang et al. | A hybrid l1-l0 layer decomposition model for tone mapping | |
| CN104408752B (en) | A kind of high dynamic range images compression method based on mixed shades mapping algorithm | |
| DE112018007721T5 (en) | Acquire and modify 3D faces using neural imaging and time tracking networks | |
| CN103810504B (en) | Image processing method and device | |
| CN111445564B (en) | Face texture image generation method, device, computer equipment and storage medium | |
| Lee et al. | Local tone mapping using the K-means algorithm and automatic gamma setting | |
| Kim et al. | Consistent tone reproduction | |
| DE112017005207T5 (en) | Method of identifying light sources, corresponding system and computer program product | |
| CN111105359B (en) | Tone mapping method for high dynamic range image | |
| Kotwal et al. | An optimization-based approach to fusion of multi-exposure, low dynamic range images | |
| CN106997608A (en) | A kind of method and device for generating halation result figure | |
| CN110493584A (en) | A kind of high dynamic range environment Visualization method, apparatus and storage medium | |
| CN111292279B (en) | Polarization image visualization method based on color image fusion | |
| CN113132696A (en) | Image tone mapping method, device, electronic equipment and storage medium | |
| CN115100337A (en) | Whole body portrait video relighting method and device based on convolutional neural network | |
| Wang et al. | Exposure Fusino Based on Shift-Invariant Discrete Wavelet Transform. | |
| Thakur et al. | Fast tone mapping for high dynamic range images | |
| Hongying et al. | Image completion by a fast and adaptive exemplar-based image inpainting | |
| Kela et al. | Illumination invariant elastic bunch graph matching for efficient face recognition | |
| CN110140150B (en) | Image processing method and device and terminal equipment | |
| Wang et al. | A multi-exposure images fusion approach for very large dynamic range scenes | |
| Chen et al. | Back-projection residual low-light image enhancement network with color correction matrix | |
| EP4358017A1 (en) | Method and apparatus for converting an hdr image file into an ldr image file | |
| Chen et al. | A fast multi-scale decomposition based tone mapping algorithm for High Dynamic Range images | |
| Yang et al. | Multi-scale histogram tone mapping algorithm for display of wide dynamic range images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |